SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure
Paper • 2608.11079 • Published • 5
AI & ML interests
None defined yet.
Recent Activity
View all activity
taesiri
submitted 3
papers to Daily Papers about 10 hours ago
taesiri
submitted 5
papers to Daily Papers 2 days ago
The Optimizer Is the Agent: Reasoning-Driven Search across Prompts, Programs, and ML Workflows
Paper • 2608.06714 • Published • 9
Characterizing the Quality Profile of AI-Generated C++ in Production
Paper • 2608.06640 • Published • 10
Modular TTT: Rethinking Test-Time Training as Composable Modules
Paper • 2608.07110 • Published • 8
Skaling: Chinchilla's Exponents Meet Kaplan's Coupling
Paper • 2608.07222 • Published • 9
Addressable Memory for Video World Models
Paper • 2608.07408 • Published • 11
taesiri
submitted 4
papers to Daily Papers 5 days ago
WorldClaw: Agentic 3D Open-World Generation at Scale
Paper • 2608.05248 • Published • 66
GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?
Paper • 2608.05747 • Published • 46
HarnessOpt-Bench: Evaluating LLMs at Harness Optimization
Paper • 2608.06301 • Published • 34
DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation
Paper • 2608.06374 • Published • 23
taesiri
submitted 4
papers to Daily Papers 6 days ago
K-EXAONE 2.0 Technical Report
Paper • 2608.04505 • Published • 25
ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation
Paper • 2608.04436 • Published • 58
HelloWorld: Enabling Socially Interactive Characters in Video World Models
Paper • 2608.05070 • Published • 37
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Paper • 2608.05131 • Published • 12
taesiri
submitted 3
papers to Daily Papers 7 days ago
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
Paper • 2608.04003 • Published • 33
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
Paper • 2608.03974 • Published • 91
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
Paper • 2608.02711 • Published • 88
taesiri
submitted a
paper to Daily Papers 8 days ago